BeGREEN: Beyond 5G Energy Efficient Networking by Hardware Acceleration and AI-Driven Management of Network Functions

M. Ghoraishi, Jose Oriol Sallent, Miguel Catalan-Cid, Guillermo Bielsa, Juan-Francisco Esteban-Rivas, V. Sark, J. G. Terán, Simon Pryor
{"title":"BeGREEN: Beyond 5G Energy Efficient Networking by Hardware Acceleration and AI-Driven Management of Network Functions","authors":"M. Ghoraishi, Jose Oriol Sallent, Miguel Catalan-Cid, Guillermo Bielsa, Juan-Francisco Esteban-Rivas, V. Sark, J. G. Terán, Simon Pryor","doi":"10.1109/EuCNC/6GSummit58263.2023.10188307","DOIUrl":null,"url":null,"abstract":"This paper presents a technical overview of BeGREEN project, a Horizon Europe, Smart Networks and Services Joint-Undertaking (SNS-JU) Phase 1 project kicked off on January 1, 2023 [1]. This paper is intended to describe BeGREEN's technical scope and objectives. These objectives aim at improving energy efficiency of the beyond 5G (B5G) networks. BeGREEN technical agenda includes analysis of the combined energy and spectrum efficiency of the B5G networks, based on massive multiple-input-multiple-output (mMIMO) scenarios. The project proposes a novel architecture that includes several innovative solutions. An offloading engine is used for hardware acceleration that is a solution for compute-heavy physical layer processing in 5G new radio (5G NR) mMIMO and beyond to improve the processing performance and energy efficiency. The architecture also includes joint communication and sensing (JCAS) for improving energy efficiency of the physical layer functions by, e.g., efficient beam-search and beam tracking, and uses reconfigurable intelligent surfaces (RIS) as an enabler for JCAS. BeGreenproposes an artificial intelligence (AI)-assisted energy-aware “Intelligent Plane” as an additional plane along with user plane and data plane, that allows the data, model, and inference to be seamlessly exchanged between network functions. The project also proposes an AI Engine that is consist of an execution environment that can host AI models and will manage their lifecycle and access to data.","PeriodicalId":65870,"journal":{"name":"公共管理高层论坛","volume":"71 1","pages":"717-722"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"公共管理高层论坛","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.1109/EuCNC/6GSummit58263.2023.10188307","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents a technical overview of BeGREEN project, a Horizon Europe, Smart Networks and Services Joint-Undertaking (SNS-JU) Phase 1 project kicked off on January 1, 2023 [1]. This paper is intended to describe BeGREEN's technical scope and objectives. These objectives aim at improving energy efficiency of the beyond 5G (B5G) networks. BeGREEN technical agenda includes analysis of the combined energy and spectrum efficiency of the B5G networks, based on massive multiple-input-multiple-output (mMIMO) scenarios. The project proposes a novel architecture that includes several innovative solutions. An offloading engine is used for hardware acceleration that is a solution for compute-heavy physical layer processing in 5G new radio (5G NR) mMIMO and beyond to improve the processing performance and energy efficiency. The architecture also includes joint communication and sensing (JCAS) for improving energy efficiency of the physical layer functions by, e.g., efficient beam-search and beam tracking, and uses reconfigurable intelligent surfaces (RIS) as an enabler for JCAS. BeGreenproposes an artificial intelligence (AI)-assisted energy-aware “Intelligent Plane” as an additional plane along with user plane and data plane, that allows the data, model, and inference to be seamlessly exchanged between network functions. The project also proposes an AI Engine that is consist of an execution environment that can host AI models and will manage their lifecycle and access to data.
BeGREEN:通过硬件加速和人工智能驱动的网络功能管理,超越5G节能网络
本文介绍了地平线欧洲智能网络和服务联合企业(SNS-JU)于2023年1月1日启动的一期项目BeGREEN项目的技术概述[1]。本文旨在描述BeGREEN的技术范围和目标。这些目标旨在提高超5G (B5G)网络的能源效率。BeGREEN技术议程包括基于大规模多输入多输出(mMIMO)场景的B5G网络的综合能量和频谱效率分析。该项目提出了一个新颖的架构,其中包括几个创新的解决方案。卸载引擎用于硬件加速,这是5G新无线电(5G NR) mMIMO及以后计算繁重的物理层处理的解决方案,以提高处理性能和能源效率。该体系结构还包括联合通信和传感(JCAS),通过高效的波束搜索和波束跟踪来提高物理层功能的能量效率,并使用可重构智能表面(RIS)作为JCAS的使能器。begreenin提出了一个人工智能(AI)辅助的能量感知“智能平面”,作为用户平面和数据平面的附加平面,使数据、模型和推理在网络功能之间无缝交换。该项目还提出了一个人工智能引擎,该引擎由一个执行环境组成,该环境可以托管人工智能模型,并将管理其生命周期和对数据的访问。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
385
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信